{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40715889", "kind": "science-record", "revision": 1, "content_hash": "sha256:597398030f91da265c1d005db90e138908c6972f0cc214a92e835819fd5e6e16", "created_at": "2026-11-01T10:25:52Z", "updated_at": "2026-11-01T10:25:52Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Deciphering hypoxia's role in hepatocellular carcinoma prognosis with single-cell approaches.", "doi": "10.1007/s12672-025-03201-y", "pmid": "40715889", "authors": null, "journal": "Discover oncology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40715889"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40715889", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40715889' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40715889", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1007/s12672-025-03201-y", "sha256": "sha256:bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1007/s12672-025-03201-y", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40715889 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40715889"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40715889"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "ac027c73b093169dcd9dba9890e115aafe2351699c54481c632e0285cd0df287", "source_hash": "bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875", "raw_response_sha256": "sha256:10f5a4675b1a7e9ac29851ac9e80a647d870242a7e872a883b1621cf3cde0499", "raw_response_chars": 4676}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "e30b78dc826daed711d2c144d5cf4dbe8309d034bd499cb72a9fb489aa52e432", "source_hash": "bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875", "raw_response_sha256": "sha256:f4b3c8d6932ded033d18a96aba0c5b8b7691de8a753edf615bb3161b2157314c", "raw_response_chars": 27255}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "4d3701935dced922ac910634d59070aa65ac0c7f77863f1eebc4c2082512934f", "source_hash": "bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875", "raw_response": "{\"parent_value\":119,\"unit\":\"key genes\",\"evidence\":\"A cumulative total of 119 key genes were pinpointed within the H2 subset, while 70 were discovered in the N2 subset.\",\"target_result\":\"119 key genes were pinpointed within the H2 subset.\",\"number_stated\":true}", "reading": {"parent_value": 119, "unit": "key genes", "evidence": "A cumulative total of 119 key genes were pinpointed within the H2 subset, while 70 were discovered in the N2 subset.", "target_result": "119 key genes were pinpointed within the H2 subset.", "number_stated": true, "source_locator": "chars 12523-12639 of source sha256 bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875"}, "recorded_at": "2026-10-31T15:26:43.820845+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "e4e12f6dafa7d6b1a56abcff7f2fe9fb265448137df1c35ab1594318316afa8b", "source_hash": "bd8a0ee5b9e5dbdf6e5bb5d8be09afec44db9ab7370956585bf82f6936569875", "raw_response": "<think>We need answer JSON object only. Need identify single numerical result headline numerical result paper states for main finding. Source text appears no headline numerical result. It has various numbers: clusters H1-H4/N1-N3, top 1%, 119 genes H2, 70 N2, 5 compounds totaling 44, correlation |Cor| >0.3, P<0.05, versions 2.22.0 etc, DOI. Registered target: \"the headline numerical result the paper states for its main finding\". Main finding CHPF, H2 high invasive, prognostic model. No stated numerical headline result, likely no number. Need set number_stated false, parent_value 0, unit \"\", evidence \"\", target_result what text states instead. Need ensure evidence exact quotation? If false, evidence empty. target_result can say text states CHPF identified cellular hypoxia states, H2 subset high invasive potential, H2-specific TF model including LRP10 MED8 NOL10 NOP58 REXO4 forecasting survival, no headline numerical result. Need not calculate. We need be careful that perhaps \"119 key genes\" might be headline numerical result? But registered target is main finding, likely no number. Source text is weird perhaps abstract truncation where numerical result missing. User emphasizes \"value paper itself states for registered target\" and if no number, false. We should state no headline numerical result. We need possibly include exact quotation in target_result? They require evidence exact contiguous quote containing number; but no number. target_result perhaps description. JSON valid no markdown.\n\nLet's parse deeply in case there is some numerical headline tied to main finding. Text abstract says no numerical values. Results: cluster counts, scores, genes, compounds. Main finding might \"constructed prognostic model\" and perhaps \"total 119 key genes in H2, 70 N2.\" But neither is headline numerical result and perhaps not exactly main finding. Registered target phrased to ask headline numerical result for main finding, likely benchmark extraction task. Need only output false if text no number for registered target. They might expect perhaps 119? Let's examine instructions: \"Read supplied paper text and find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints. The evidence must be an exact, contiguous quotation from SOURCE TEXT that contains the number; do not shorten it, do not add an ellipsis and do not paraphrase it. Attribution may be carried by the text's own wording: a number may be attached to the target by a parenthetical list, by the word 'respectively', or by words that name the target directly. When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves. If the text states no number for the registered target, set number_stated to false, leave parent_value at 0, leave unit and evidence empty, and say in target_result what the text does state instead.\"\n\nSo yes need determine whether number. Text may have 119 and 70, but are these headline numerical result for main finding? The registered target is generic \"the headline numerical result the paper states for its main finding\". Main finding: CHPF model based on H2-specific TFs; no performance metric, risk score threshold etc. Numbers 119/70 are associated key genes, likely not headline. The paper could have a missing section about CHPF construction and survival. No numerical result. Therefore false.\n\nNeed target_result maybe exact quote \"The model demonstrated significant predictive value for lifespan of patients as verified in the TCGA dataset and an external validation group.\" This states qualitative. Could include quote but target_result could be \"No headline numerical result is stated; the paper reports...\" It says \"say in target_result what the text does state instead.\" We can state: \"No headline numerical result is stated. The text reports that the H2 subpopulation had the highest invasive potential and that a model based on H2-specific transcription factors (LRP10, MED8, NOL10, NOP58, REXO4) had significant predictive value for patient lifespan in TCGA and an external validation group.\" Good.\n\nEnsure no numerical values in target_result? Maybe avoids accidental confusion; not required. It can say H2 etc though. Fine. JSON schema fields exactly.\n\nPotential concern: target_result should quote source perhaps exact. Could say \"The paper states that the H2 subpopulation displayed the utmost invasive potential and that the model demonstrated significant predictive value for lifespan of patients as verified in the TCGA dataset and an external validation group, without a headline numerical result.\" That is paraphrase but target_result not evidence and they specifically say what text states instead. Fine.\n\nNeed no additional prose.</think>\n\n{\"parent_value\":0,\"unit\":\"\",\"evidence\":\"\",\"target_result\":\"No headline numerical result is stated. The paper reports that the H2 subpopulation displayed the highest invasive potential and that a prognostic model based on H2-specific transcription factors demonstrated significant predictive value for patient lifespan in the TCGA dataset and an external validation group.\",\"number_stated\":false}", "reading": {"parent_value": 0, "unit": "", "evidence": "", "target_result": "No headline numerical result is stated. The paper reports that the H2 subpopulation displayed the highest invasive potential and that a prognostic model based on H2-specific transcription factors demonstrated significant predictive value for patient lifespan in the TCGA dataset and an external validation group.", "number_stated": false, "source_locator": null}, "recorded_at": "2026-10-31T15:26:47.543996+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A prognostic model based on five H2-specific transcription factors—LRP10, MED8, NOL10, NOP58, and REXO4—was reported to have significant predictive value for patient lifespan in the TCGA dataset and an external validation group, although no numerical performance statistic for the model is stated in the supplied text.", "minimax_alt": "The paper reports a CHPF prognostic model based on H2-specific transcription factors LRP10, MED8, NOL10, NOP58 and REXO4 that demonstrated significant predictive value for patient lifespan in the TCGA dataset and an external validation group. No explicit numerical performance result is stated in the supplied text.", "decisive": false}, "analysis_methods": {"minimax": ["single-cell RNA sequencing", "UMAP", "Weighted correlation network analysis (WGCNA)", "CellChat", "Monocle trajectory analysis", "inferCNV", "SCENIC with GRNboost2", "CytoTRACE", "GSVA", "Cox regression analysis", "Kaplan-Meier survival analysis"], "minimax_alt": ["single-cell RNA sequencing", "UMAP", "Weighted correlation network analysis (WGCNA)", "CellChat", "Monocle2", "infercnv", "SCENIC", "GRNboost2", "CytoTRACE", "GSVA", "Cox regression analysis", "Kaplan-Meier survival analysis"], "decisive": false}, "statistical_method": {"minimax": "Cox regression analysis and Kaplan-Meier survival analysis using the survival package in R", "minimax_alt": "Cox regression analysis and Kaplan-Meier survival analysis", "decisive": true}, "number_stated": {"minimax": true, "minimax_alt": false, "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:cc9a626ab339deff894bcf9ed107add68cdb29add4ae944d03a184164e2908fa", "type": "sep_package", "label": "SEP v1 package for pmid:40715889"}], "activities": [{"id": "activity:conversion:pmid:40715889", "type": "conversion", "used": ["package:cc9a626ab339deff894bcf9ed107add68cdb29add4ae944d03a184164e2908fa"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "1235d2d7-5f13-4d32-924c-5037aa9fe0b4", "parent_hash": "cc9a626ab339deff894bcf9ed107add68cdb29add4ae944d03a184164e2908fa", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40715889 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40715889' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:12:29+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}